Models
431 models you can call with one Phantom key, at today’s prices.
phantom-1
One model id for every endpoint. On chat it picks one of three models for each new conversation and keeps the conversation on it for an hour. Ask it to use only providers that keep no data, and it skips the free model. Each response names the model that ran.
phantom-1How phantom-1 picks a model| Endpoint | Model | Input / 1M | Output / 1M | Status |
|---|---|---|---|---|
Chat Routine formatting and extraction | nvidia/nemotron-3.5-lightning-free | Free | Free | Up |
Chat Most requests, and prompts over 20,000 tokens | deepseek/deepseek-v4.1-flash | $0.07875 | $0.315 | Up |
Chat Race conditions, proofs and contest problems | anthropic/claude-sonnet-5.5 | $2.10 | $10.50 | Up |
Chat with images | alibaba/qwen3.7-flash | $0.0315 | $0.1365 | Up |
Embeddings | openai/text-embedding-3-small | $0.021 | n/a | Up |
Rerank | voyage/rerank-3 | $0.0525 | n/a | Up |
Images | bfl/flux-pro-1.1 | $0.042 / image | Up | |
Video | alibaba/wan-v2.6-t2v | $0.1575 / second | Up | |
Speech | openai/tts-1 | $15.75 / 1M characters | Up | |
Transcription | openai/whisper-1 | $0.0063 / minute | Up | |
All models
Send any id below as model on the endpoint for its kind. Older models stay hidden until you search for one or show them.
87 of 431 models
OpenAI4
openai/gpt-6.1-sol$2.10 in, $10.50 out per 1M, 1.1M context
reasoning · tool use · vision · file input · no training
openai/gpt-6-luna$0.105 in, $0.525 out per 1M, 1.1M context
reasoning · tool use · vision · file input · no training
openai/gpt-oss-safeguard-20b$0.0735 in, $0.21 out per 1M, 128K context
reasoning · tool use · zero retention · no training
openai/gpt-oss-20b$0.0315 in, $0.147 out per 1M, 131K context
reasoning · tool use · zero retention · no training
Anthropic2
anthropic/claude-haiku-5.5$0.105 in, $0.525 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
anthropic/claude-sonnet-5.5$2.10 in, $10.50 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
Google6
google/gemini-4-argon$2.10 in, $10.50 out per 1M, 1M context
reasoning · tool use · vision · file input · no training
google/gemini-nano-banana-2.1$1.575 in, $7.875 out per 1M, 131K context
reasoning · vision · web search · image generation · no training
google/gemini-3.8-flash$0.7875 in, $3.9375 out per 1M, 1M context
reasoning · tool use · vision · file input · no training
google/gemma-4-26b-a4b-it$0.1575 in, $0.63 out per 1M, 262K context
reasoning · tool use · vision · file input
google/gemma-4-31b-it$0.147 in, $0.42 out per 1M, 262K context
reasoning · tool use · vision · file input
google/gemini-2.5-flash-lite$0.105 in, $0.42 out per 1M, 1M context
reasoning · tool use · vision · file input · no training
xAI7
spacexai/grok-4.7$2.10 in, $6.30 out per 1M, 500K context
reasoning · tool use · vision · zero retention · no training
spacexai/grok-4.5$2.10 in, $6.30 out per 1M, 500K context
reasoning · tool use · vision · file input · zero retention · no training
spacexai/grok-build-0.1$1.05 in, $2.10 out per 1M, 256K context
reasoning · tool use · vision · web search · zero retention · no training
spacexai/grok-4.3$1.3125 in, $2.625 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
spacexai/grok-4.20-multi-agent-beta$1.3125 in, $2.625 out per 1M, 2M context
reasoning · tool use · vision · file input · zero retention · no training
spacexai/grok-4.20-non-reasoning-beta$1.3125 in, $2.625 out per 1M, 2M context
tool use · vision · file input · web search · zero retention · no training
Meta3
meta/muse-spark-open$1.3125 in, $4.4625 out per 1M, 1M context
reasoning · tool use · vision · zero retention · no training
meta/muse-wonder-1.0$4.20 in, $21.00 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
meta/muse-spark-1.3$1.3125 in, $4.4625 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
DeepSeek1
deepseek/deepseek-v4.1-flash$0.07875 in, $0.315 out per 1M, 1M context
reasoning · tool use · vision
Mistral6
mistral/mistral-large-4$0.714 in, $2.1945 out per 1M, 524K context
reasoning · tool use · vision · zero retention · no training
mistral/ministral-14b$0.21 in, $0.21 out per 1M, 262K context
tool use · vision · file input · zero retention · no training
mistral/mistral-large-3$0.525 in, $1.575 out per 1M, 262K context
tool use · vision · zero retention · no training
mistral/ministral-3b$0.105 in, $0.105 out per 1M, 131K context
tool use · vision · zero retention · no training
mistral/ministral-8b$0.1575 in, $0.1575 out per 1M, 262K context
tool use · vision · zero retention · no training
mistral/mistral-nemo$0.03045 in, $0.0315 out per 1M, 131K context
tool use · zero retention · no training
Qwen7
alibaba/qwen3.8-max-prime$4.20 in, $12.60 out per 1M, 1M context
reasoning · tool use · vision · zero retention · no training
alibaba/qwen3.8-omni-flash$0.1575 in, $0.4935 out per 1M, 1M context
reasoning · tool use · vision · zero retention · no training
alibaba/qwen3.8-flash$0.1575 in, $0.4935 out per 1M, 991K context
reasoning · tool use · vision · file input · zero retention · no training
alibaba/qwen3.8-27b$0.525 in, $3.15 out per 1M, 1M context
reasoning · tool use · vision · file input
alibaba/qwen3.7-flash$0.0315 in, $0.1365 out per 1M, 991K context
reasoning · tool use · vision · file input · zero retention · no training
alibaba/qwen3.7-plus$0.42 in, $1.68 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
Moonshot5
moonshotai/kimi-k3$3.15 in, $15.75 out per 1M, 1M context
reasoning · tool use · vision · file input
moonshotai/kimi-k2.7-code$0.9975 in, $4.20 out per 1M, 256K context
reasoning · tool use · vision · file input · zero retention · no training
moonshotai/kimi-k2.6$0.9975 in, $4.20 out per 1M, 262K context
reasoning · tool use · vision
moonshotai/kimi-k2.5$0.63 in, $3.15 out per 1M, 256K context
reasoning · tool use · vision
moonshotai/kimi-k2$0.5985 in, $2.415 out per 1M, 131K context
tool use
Z.ai3
zai/glm-5.3-flash$0.1575 in, $0.525 out per 1M, 1M context
reasoning · tool use · vision
zai/glm-5v-turbo$1.26 in, $4.20 out per 1M, 200K context
reasoning · tool use · vision · file input
zai/glm-4.7-flash$0.0735 in, $0.42 out per 1M, 200K context
reasoning · tool use
MiniMax1
minimax/minimax-m3$0.315 in, $1.26 out per 1M, 512K context
reasoning · tool use · vision · file input
NVIDIA2
nvidia/nemotron-3.5-super-vl$0.21 in, $0.525 out per 1M, 1M context
reasoning · tool use · vision
nvidia/nemotron-3.5-lightning-freeFree, 1M context
reasoning · tool use
Amazon3
amazon/nova-2-lite$0.315 in, $2.625 out per 1M, 1M context
reasoning · tool use · vision · file input · zero retention · no training
amazon/nova-lite$0.063 in, $0.252 out per 1M, 300K context
tool use · vision · file input · zero retention · no training
amazon/nova-micro$0.03675 in, $0.147 out per 1M, 128K context
tool use · zero retention · no training
arcee-ai1
arcee-ai/trinity-large-thinking$0.2625 in, $0.84 out per 1M, 262K context
reasoning · tool use
bytedance3
bytedance/seed-2.1-turbo$0.525 in, $2.625 out per 1M, 262K context
reasoning · tool use · vision · no training
bytedance/seed-1.6$0.2625 in, $2.10 out per 1M, 256K context
reasoning · tool use · vision · no training
bytedance/seed-1.8$0.2625 in, $2.10 out per 1M, 256K context
reasoning · tool use · vision · no training
callstack1
callstack/apex$0.525 in, $3.15 out per 1M, 262K context
reasoning · tool use · vision
cohere1
cohere/command-a$2.625 in, $10.50 out per 1M, 256K context
tool use · no training
elorian1
elorian/glimpse$0.63 in, $3.15 out per 1M, 220K context
reasoning · vision
fireworks1
fireworks/ember-1$3.15 in, $15.75 out per 1M, 1M context
reasoning · tool use · vision · zero retention · no training
inception1
inception/mercury-2.5$0.042 in, $0.1575 out per 1M, 260K context
reasoning · tool use · no training
inclusionai3
inclusionai/ling-3.1-flash$0.315 in, $0.945 out per 1M, 262K context
reasoning · tool use
inclusionai/ling-3.0-flash-vl$0.07875 in, $0.231 out per 1M, 256K context
reasoning · tool use · vision
inclusionai/ling-3.0-flash$0.02205 in, $0.06615 out per 1M, 256K context
reasoning · tool use
inference-net2
inference-net/schematron-v2-small$0.0525 in, $0.2415 out per 1M, 128K context
inference-net/schematron-v2-turbo$0.0315 in, $0.1575 out per 1M, 128K context
interfaze1
interfaze/interfaze-beta$1.575 in, $3.675 out per 1M, 1M context
reasoning · tool use · vision · file input · no training
liquid1
liquid/lfm2.5-24b-a2b$0.0525 in, $0.735 out per 1M, 128K context
reasoning · tool use
mixedbread1
mixedbread/toast-1$0.315 in, $0.756 out per 1M, 131K context
tool use
morph1
morph/morph-v3-large$0.945 in, $1.995 out per 1M, 82K context
zero retention · no training
perplexity1
perplexity/sonar$0.2625 in, $2.625 out per 1M, 127K context
reasoning · vision · web search · no training
quiverai2
quiverai/arrow-2$4.20 in, $21.00 out per 1M, 131K context
reasoning · tool use · vision · image generation
quiverai/arrow-2-telos$6.30 in, $31.50 out per 1M, 131K context
reasoning · tool use · vision · image generation
reflection2
reflection/beamFree, 1M context
reasoning · tool use
reflection/beam-freeFree, 1M context
reasoning · tool use
sakana3
sakana/fugu-max$2.10 in, $6.30 out per 1M, 1M context
reasoning · tool use · vision · no training
sakana/fugu-ultra-v2$5.25 in, $31.50 out per 1M, 1M context
reasoning · tool use · vision · no training
sakana/namazu$0.9975 in, $4.20 out per 1M, 256K context
reasoning · tool use · vision · file input · no training
stealth1
stealth/cat-jamFree, 1M context
reasoning · tool use
stepfun1
stepfun/step-3.7-flash$0.21 in, $1.2075 out per 1M, 256K context
reasoning · tool use · vision
tencent3
tencent/hy3$0.147 in, $0.609 out per 1M, 262K context
reasoning · tool use
tencent/hy-mt2-lite$0.0462 in, $0.18585 out per 1M, 8K context
tencent/hy-mt2-plus$0.0777 in, $0.30975 out per 1M, 8K context
thinkingmachines1
thinkingmachines/inkling-small$0.4725 in, $1.26 out per 1M, 1M context
reasoning · tool use · vision · file input
xiaomi5
xiaomi/mimo-v2.6-flash$0.147 in, $0.294 out per 1M, 1M context
reasoning · tool use · vision
xiaomi/mimo-v2.6-pro$0.45675 in, $0.9135 out per 1M, 1M context
reasoning · tool use · vision
xiaomi/mimo-v2.6-pro-ultraspeed$4.5675 in, $9.135 out per 1M, 1M context
reasoning · tool use · vision
xiaomi/mimo-v2.5$0.147 in, $0.294 out per 1M, 1.1M context
reasoning · tool use · vision
xiaomi/mimo-v2.5-pro$0.319725 in, $0.63945 out per 1M, 1.1M context
reasoning · tool use